About Saynetic
Saynetic is a free tool for adding animated, word-by-word captions to short vertical videos for TikTok, Instagram Reels and YouTube Shorts. Your video never leaves your device.
How it works
- Open a video (MP4, MOV or WebM, up to 3 minutes).
- Transcribe it on your device. An open-source speech recognition model (Whisper) runs inside your browser and gives every word its own timestamp. The model downloads once, the first time you transcribe, and is then kept in your browser's cache.
- Fix anything in the transcript: spelling, timing, or missing words.
- Pick a caption style (32 styles, with categories, search and favourites), tweak fonts and colors, add emojis, censor words or bleep them, and add effects such as a blurred 9:16 background.
- Export an MP4 with the captions burned in, or download SRT/VTT subtitle files.
Why your video stays private
There is no upload step and no account. Once the page has loaded, your browser does all the work: reading the audio, recognising speech, drawing captions and encoding the finished video. Your video, its audio, your transcript and your edits are never sent to us or to anyone else.
The site itself is supported by ads and uses privacy-friendly page-view statistics. See the privacy policy for exactly what that involves.
What you need
- A recent version of Chrome, Edge, Safari or Firefox, on a computer or phone.
- Enough free memory for the speech model. On phones the smaller “Fast” model is recommended.
Credits
- Speech recognition: OpenAI Whisper (MIT), ONNX exports by the ONNX Community, run with Transformers.js and ONNX Runtime Web.
- Video processing: Mediabunny; compatibility encoder: ffmpeg.wasm.
- Fonts: 30 families under the SIL Open Font License (including Montserrat, Poppins, Inter, Anton, Playfair Display, Oswald and Press Start 2P) and Permanent Marker under the Apache License 2.0, all self-hosted (full list and licenses).
- Emoji graphics: Twemoji © Twitter, Inc and other contributors, licensed under CC-BY 4.0 (details).